Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751623AbbGMEWB (ORCPT ); Mon, 13 Jul 2015 00:22:01 -0400 Received: from userp1040.oracle.com ([156.151.31.81]:20178 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751522AbbGMEV7 (ORCPT ); Mon, 13 Jul 2015 00:21:59 -0400 From: Mike Kravetz To: linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-api@vger.kernel.org Cc: Dave Hansen , Naoya Horiguchi , David Rientjes , Hugh Dickins , Davidlohr Bueso , Aneesh Kumar , Hillf Danton , Christoph Hellwig , Andrew Morton , Michal Hocko , Mike Kravetz Subject: [PATCH v3 02/10] mm/hugetlb: add region_del() to delete a specific range of entries Date: Sun, 12 Jul 2015 21:21:00 -0700 Message-Id: <1436761268-6397-3-git-send-email-mike.kravetz@oracle.com> X-Mailer: git-send-email 2.1.0 In-Reply-To: <1436761268-6397-1-git-send-email-mike.kravetz@oracle.com> References: <1436761268-6397-1-git-send-email-mike.kravetz@oracle.com> X-Source-IP: aserv0021.oracle.com [141.146.126.233] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5173 Lines: 164 fallocate hole punch will want to remove a specific range of pages. The existing region_truncate() routine deletes all region/reserve map entries after a specified offset. region_del() will provide this same functionality if the end of region is specified as LONG_MAX. Hence, region_del() can replace region_truncate(). Unlike region_truncate(), region_del() can return an error in the rare case where it can not allocate memory for a region descriptor. This ONLY happens in the case where an existing region must be split. Current callers passing LONG_MAX as end of range will never experience this error and do not need to deal with error handling. Future callers of region_del() (such as fallocate hole punch) will need to handle this error. Signed-off-by: Mike Kravetz --- mm/hugetlb.c | 99 ++++++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 73 insertions(+), 26 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 241d16d..a5c8b3c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -461,43 +461,90 @@ static void region_abort(struct resv_map *resv, long f, long t) } /* - * Truncate the reserve map at index 'end'. Modify/truncate any - * region which contains end. Delete any regions past end. - * Return the number of huge pages removed from the map. + * Delete the specified range [f, t) from the reserve map. If the + * t parameter is LONG_MAX, this indicates that ALL regions after f + * should be deleted. Locate the regions which intersect [f, t) + * and either trim, delete or split the existing regions. + * + * Returns the number of huge pages deleted from the reserve map. + * In the normal case, the return value is zero or more. In the + * case where a region must be split, a new region descriptor must + * be allocated. If the allocation fails, -ENOMEM will be returned. + * NOTE: If the parameter t == LONG_MAX, then we will never split + * a region and possibly return -ENOMEM. Callers specifying + * t == LONG_MAX do not need to check for -ENOMEM error. */ -static long region_truncate(struct resv_map *resv, long end) +static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; - long chg = 0; + struct file_region *nrg = NULL; + long del = 0; +retry: spin_lock(&resv->lock); - /* Locate the region we are either in or before. */ - list_for_each_entry(rg, head, link) - if (end <= rg->to) + list_for_each_entry_safe(rg, trg, head, link) { + if (rg->to <= f) + continue; + if (rg->from >= t) break; - if (&rg->link == head) - goto out; - /* If we are in the middle of a region then adjust it. */ - if (end > rg->from) { - chg = rg->to - end; - rg->to = end; - rg = list_entry(rg->link.next, typeof(*rg), link); - } + if (f > rg->from && t < rg->to) { /* Must split region */ + /* + * Check for an entry in the cache before dropping + * lock and attempting allocation. + */ + if (!nrg && + resv->rgn_cache_count > resv->adds_in_progress) { + nrg = list_first_entry(&resv->rgn_cache, + struct file_region, + link); + list_del(&nrg->link); + resv->rgn_cache_count--; + } - /* Drop any remaining regions. */ - list_for_each_entry_safe(rg, trg, rg->link.prev, link) { - if (&rg->link == head) + if (!nrg) { + spin_unlock(&resv->lock); + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); + if (!nrg) + return -ENOMEM; + goto retry; + } + + del += t - f; + + /* New entry for end of split region */ + nrg->from = t; + nrg->to = rg->to; + INIT_LIST_HEAD(&nrg->link); + + /* Original entry is trimmed */ + rg->to = f; + + list_add(&nrg->link, &rg->link); + nrg = NULL; break; - chg += rg->to - rg->from; - list_del(&rg->link); - kfree(rg); + } + + if (f <= rg->from && t >= rg->to) { /* Remove entire region */ + del += rg->to - rg->from; + list_del(&rg->link); + kfree(rg); + continue; + } + + if (f <= rg->from) { /* Trim beginning of region */ + del += t - rg->from; + rg->from = t; + } else { /* Trim end of region */ + del += rg->to - f; + rg->to = f; + } } -out: spin_unlock(&resv->lock); - return chg; + kfree(nrg); + return del; } /* @@ -648,7 +695,7 @@ void resv_map_release(struct kref *ref) struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ - region_truncate(resv_map, 0); + region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { @@ -3871,7 +3918,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) long gbl_reserve; if (resv_map) - chg = region_truncate(resv_map, offset); + chg = region_del(resv_map, offset, LONG_MAX); spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); -- 2.1.0 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/